{"total":40,"rows":[{"id":"2205.07540","title":"The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues","created":"2022-05-16","cited_by_count":79,"area":null},{"id":"2412.09416","title":"Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors","created":"2024-12-12","cited_by_count":61,"area":null},{"id":"2502.18940","title":"MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors","created":"2025-02-26","cited_by_count":49,"area":null},{"id":"2409.16490","title":"Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs","created":"2024-09-24","cited_by_count":46,"area":null},{"id":"2211.11772","title":"The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2503.06424","title":"Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues","created":"2025-03-09","cited_by_count":43,"area":null},{"id":"2204.09652","title":"The TalkMoves Dataset: K-12 Mathematics Lesson Transcripts Annotated for Teacher and Student Discursive Moves","created":"2022-04-06","cited_by_count":38,"area":null},{"id":"2301.09919","title":"Opportunities and Challenges in Neural Dialog Tutoring","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2208.04715","title":"Computationally Identifying Funneling and Focusing Questions in Classroom Discourse","created":"2022-07-08","cited_by_count":15,"area":null},{"id":"2402.05111","title":"Edu-ConvoKit: An Open-Source Library for Education Conversation Data","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2505.16931","title":"PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2311.07589","title":"Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2404.02444","title":"The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2310.01132","title":"Automated Evaluation of Classroom Instructional Support with LLMs and BoWs: Connecting Global Predictions to Specific Feedback","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2403.08272","title":"RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Education","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2307.04274","title":"Assessing the efficacy of large language models in generating accurate teacher responses","created":"2023-07-09","cited_by_count":6,"area":null},{"id":"2507.22753","title":"Opportunities and Challenges of LLMs in Education: An NLP Perspective","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2410.07147","title":"Taking a turn for the better: Conversation redirection throughout the course of mental-health therapy","created":"2024-10-09","cited_by_count":5,"area":null},{"id":"2510.22581","title":"Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems","created":"2025-10-26","cited_by_count":5,"area":null},{"id":"2309.12367","title":"Examining the Influence of Varied Levels of Domain Knowledge Base Inclusion in GPT-based Intelligent Tutors","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2311.10749","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2406.08680","title":"Analyzing Large Language Models for Classroom Discussion Assessment","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2505.18549","title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2507.06910","title":"Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues","created":"2025-07-09","cited_by_count":4,"area":null},{"id":"2307.03319","title":"Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2505.07902","title":"Multimodal Assessment of Classroom Discourse Quality: A Text-Centered Attention-Based Multi-Task Learning Approach","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2311.14067","title":"Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2412.13395","title":"Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2509.17961","title":"Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2605.07409","title":"The Proxy Presumption: From Semantic Embeddings to Valid Social Measures","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2309.13243","title":"ChEDDAR: Student-ChatGPT Dialogue in EFL Writing Education","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2507.05385","title":"EduCoder: An Open-Source Annotation System for Education Transcript Data","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2602.09269","title":"Measuring Inclusion in Interaction: Inclusion Analytics for Human-AI Collaborative Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.17314","title":"Open Datasets in Learning Analytics: Trends, Challenges, and Best PRACTICE","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.05778","title":"Tutor Move Taxonomy: A Theory-Aligned Framework for Analyzing Instructional Moves in Tutoring","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.07583","title":"CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.13712","title":"Multimodal Speaker Identification in Classroom Environments","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.27043","title":"EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38907","title":"Characterizing Questioning Patterns and Student Engagement Through Contextual Analysis of Real-Time Classroom Interactions","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}